Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3153 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.1081. Min Act: -0.1700
Data Index: 156578 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.0556. Min Act: -0.1700
Data Index: 984766 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.0556. Min Act: -0.1700
Data Index: 8060250 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.0556. Min Act: -0.1699
Data Index: 2095669 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.0382. Min Act: -0.1700
Data Index: 1960818 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.0208. Min Act: -0.1700
Data Index: 602502 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.0208. Min Act: -0.1700
Data Index: 7560183 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.0034. Min Act: -0.1700
Data Index: 6030389 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.0034. Min Act: -0.1700
Data Index: 3747647 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.0034. Min Act: -0.1700
Data Index: 3103883 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.0034. Min Act: -0.1700
Data Index: 6066792 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.0034. Min Act: -0.1700
Data Index: 5752135 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.0034. Min Act: -0.1700
Data Index: 7659780 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.0034. Min Act: -0.1700
Data Index: 7827129 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.0034. Min Act: -0.1700
Data Index: 19933 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.0034. Min Act: -0.1700
Data Index: 4820660 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.0034. Min Act: -0.1699
Data Index: 2936540 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1081. Min Range: -1.1081
Max Act: 1.0208. Min Act: -0.1700
Data Index: 1720751 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1081. Min Range: -1.1081
Max Act: 0.9860. Min Act: -0.1700
Data Index: 4292742 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1081. Min Range: -1.1081
Max Act: 0.9860. Min Act: -0.1700
Data Index: 5061804 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19